Abstractive Summarization of Multi Documents using Fairseq

Senthil Kumar, Akash (2023) Abstractive Summarization of Multi Documents using Fairseq. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (584kB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Multi document summarization can save time browsing several sources of information . The aim of this research proposal is to perform multi document summarization where the objective is to summarize text obtained from different sources/documents and the summary generated by the model will be a combined summary of multiple the sources. Another objective is to minimise redundancy of information that might result from the process of multi document summarization. Especially, the same information might be repeated across documents.. NLP based sequence to sequence models are deep learning model that are becoming in generating summary. . Fairseq is used in this research project to generate the summary where the input is given from the multiple sources. Rouge score has been used as the evaluation metric resulting to Rouge 1:- 0.31, Rouge 2:- 0.08, Rouge L:- 0.15 are the obtained ROUGE Metric scores.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Rifai, Hicham UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	02 Jan 2025 13:59
Last Modified:	02 Jan 2025 13:59
URI:	https://norma.ncirl.ie/id/eprint/7266

Actions (login required)

View Item